# In Defense of Online Models for Video Instance Segmentation

arXiv: https://arxiv.org/abs/2207.10661 · HTML: https://mlsanity.com/paper/2207.10661/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 52 references that are in the map.
- First posted on arXiv 21 Jul 2022.

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Video Instance Segmentation](https://mlsanity.com/paper/1905.04804/) (2019)
- [Tracking without bells and whistles](https://mlsanity.com/paper/1903.05625/) (2019)
- [TransTrack: Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2012.15460/) (2020)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Self-supervised Co-training for Video Representation Learning](https://mlsanity.com/paper/2010.09709/) (2020)
- [MOTS: Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/1902.03604/) (2019)
- [Quasi-Dense Similarity Learning for Multiple Object Tracking](https://mlsanity.com/paper/2006.06664/) (2020)

## Built on by (most cited first, 30 of 97)

- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training](https://mlsanity.com/paper/2208.02245/) (2022)
- [DVIS: Decoupled Video Instance Segmentation Framework](https://mlsanity.com/paper/2306.03413/) (2023)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [General Object Foundation Model for Images and Videos at Scale](https://mlsanity.com/paper/2312.09158/) (2023)
- [OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation](https://mlsanity.com/paper/2307.09356/) (2023)
- [A Generalized Framework for Video Instance Segmentation](https://mlsanity.com/paper/2211.08834/) (2022)
- [CTVIS: Consistent Training for Online Video Instance Segmentation](https://mlsanity.com/paper/2307.12616/) (2023)
- [Matching Anything by Segmenting Anything](https://mlsanity.com/paper/2406.04221/) (2024)
- [Spectrum-guided Multi-granularity Referring Video Object Segmentation](https://mlsanity.com/paper/2307.13537/) (2023)
- [TarViS: A Unified Approach for Target-based Video Segmentation](https://mlsanity.com/paper/2301.02657/) (2023)
- [HyperSeg: Towards Universal Visual Segmentation with Large Language Model](https://mlsanity.com/paper/2411.17606/) (2024)
- [UniVS: Unified and Universal Video Segmentation with Prompts as Queries](https://mlsanity.com/paper/2402.18115/) (2024)
- [Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation](https://mlsanity.com/paper/2403.12042/) (2024)
- [OpenVIS: Open-vocabulary Video Instance Segmentation](https://mlsanity.com/paper/2305.16835/) (2023)
- [Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation](https://mlsanity.com/paper/2304.04694/) (2023)
- [Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation](https://mlsanity.com/paper/2303.12782/) (2023)
- [UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces](https://mlsanity.com/paper/2312.15715/) (2023)
- [Mask-Free Video Instance Segmentation](https://mlsanity.com/paper/2303.15904/) (2023)
- [OmniTracker: Unifying Object Tracking by Tracking-with-Detection](https://mlsanity.com/paper/2303.12079/) (2023)
- [DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion](https://mlsanity.com/paper/2303.14863/) (2023)
- [TCOVIS: Temporally Consistent Online Video Instance Segmentation](https://mlsanity.com/paper/2309.11857/) (2023)
- [ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation](https://mlsanity.com/paper/2412.09754/) (2024)
- [Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2501.04670/) (2025)
- [Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation](https://mlsanity.com/paper/2407.07427/) (2024)
- [UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model](https://mlsanity.com/paper/2305.12659/) (2023)
- [MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos](https://mlsanity.com/paper/2303.14395/) (2023)

## Abstract (arXiv)

In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance. However, online methods have their inherent advantage in handling long video sequences and ongoing videos while offline models fail due to the limit of computational resources. Therefore, it would be highly desirable if online models can achieve comparable or even better performance than offline models. By dissecting current online models and offline models, we demonstrate that the main cause of the performance gap is the error-prone association between frames caused by the similar appearance among different instances in the feature space. Observing this, we propose an online framework based on contrastive learning that is able to learn more discriminative instance embeddings for association and fully exploit history information for stability. Despite its simplicity, our method outperforms all online and offline methods on three benchmarks. Specifically, we achieve 49.5 AP on YouTube-VIS 2019, a significant improvement of 13.2 AP and 2.1 AP over the prior online and offline art, respectively. Moreover, we achieve 30.2 AP on OVIS, a more challenging dataset with significant crowding and occlusions, surpassing the prior art by 14.8 AP. The proposed method won first place in the video instance segmentation track of the 4th Large-scale Video Object Segmentation Challenge (CVPR2022). We hope the simplicity and effectiveness of our method, as well as our insight into current methods, could shed light on the exploration of VIS models.